Premium
Bayesian student modeling and the problem of parameter specification
Author(s) -
Millán E,
Agosta J M,
Pérez de la Cruz J L
Publication year - 2001
Publication title -
british journal of educational technology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.79
H-Index - 95
eISSN - 1467-8535
pISSN - 0007-1013
DOI - 10.1111/1467-8535.00188
Subject(s) - computer science , bayesian network , conditional independence , independence (probability theory) , bayesian probability , causal model , machine learning , meaning (existential) , process (computing) , theoretical computer science , artificial intelligence , variable order bayesian network , algorithm , bayesian inference , mathematics , programming language , psychology , statistics , psychotherapist
In this paper, the application of Bayesian networks to student modeling is discussed. A review of related work is made, and then the structural model is defined. Two of the most commonly cited reasons for not using Bayesian networks in student modeling are the computational complexity of the algorithms and the difficulty of the knowledge acquisition process . We propose an approach to simplify knowledge acquisition. Our approach applies causal independence to factor the conditional probabilities and decrease the parameters required for each question to a number linear in the number of concepts. This also provides the new parameters with an intuitive meaning that makes their specification easier. Finally, we present an example to illustrate the use of our approach.